A Real-time Breakdown Prediction Method for Urban Expressway On-ramp Bottlenecks

2017 3rd International Conference on Environmental Science and Material Application

生态环境科学;材料科学

Ye, Yingjun^1 ; Qin, Guoyang^1 ; Sun, Jian^1 ; Liu, Qiyuan^1,2

Department of Traffic Engineering, Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai

201804, China^1

Huachuan Transportation Technology CO. LTD, Suzhou

215500, China^2

关键词: Classification accuracy;    Dynamic environments;    Geometry features;    Prediction accuracy;    Prediction methods;    Prediction performance;    Shanghai , China;    Unified Modeling;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/108/3/032059/pdf
DOI  :  10.1088/1755-1315/108/3/032059

来源: IOP

【 摘 要 】

Breakdown occurrence on expressway is considered to relate with various factors. Therefore, to investigate the association between breakdowns and these factors, a Bayesian network (BN) model is adopted in this paper. Based on the breakdown events identified at 10 urban expressways on-ramp in Shanghai, China, 23 parameters before breakdowns are extracted, including dynamic environment conditions aggregated with 5-minutes and static geometry features. Different time periods data are used to predict breakdown. Results indicate that the models using 5-10 min data prior to breakdown performs the best prediction, with the prediction accuracies higher than 73%. Moreover, one unified model for all bottlenecks is also built and shows reasonably good prediction performance with the classification accuracy of breakdowns about 75%, at best. Additionally, to simplify the model parameter input, the random forests (RF) model is adopted to identify the key variables. Modeling with the selected 7 parameters, the refined BN model can predict breakdown with adequate accuracy.